Innovations in Neural Data-to-text Generation: A Survey

arXiv:2207.12571v3 Announce Type: replace
Abstract: The neural boom that has sparked natural language processing (NLP) research through the last decade has similarly led to significant innovations in data-to-text generation (DTG). This survey offers a consolidated view into the neural DTG paradigm with a structured examination of the approaches, benchmark datasets, and evaluation protocols. This survey draws boundaries separating DTG from the rest of the natural language generation (NLG) landscape, encompassing an up-to-date synthesis of the literature, and highlighting the stages …

abstract arxiv benchmark boom cs.cl data datasets evaluation innovations language language processing natural natural language natural language processing nlp paradigm processing research survey text text generation through type view